Search results for "55"
showing 10 items of 2320 documents
Research on Vocabulary Sizes and Codebook Universality
2014
Published version of an article in the journal: Abstract and Applied Analysis. Also available from the publisher at: http://dx.doi.org/10.1155/2014/697245 Open Access Codebook is an effective image representation method. By clustering in local image descriptors, a codebook is shown to be a distinctive image feature and widely applied in object classification. In almost all existing works on codebooks, the building of the visual vocabulary follows a basic routine, that is, extracting local image descriptors and clustering with a user-designated number of clusters. The problem with this routine lies in that building a codebook for each single dataset is not efficient. In order to deal with th…
An exploration of semi-supervised text classification
2021
Master's thesis in Information- and communication technology (IKT590) Obtaining labeled data to train natural language machine learning algorithms is often expensive and time-consuming, while unlabeled data usually is free and easy to get. Frequently a large amount of labeled data is required by supervised learning to achieve good text classification performance. Semi-supervised learning (SSL) for text classification is an exciting area of research. SSL is a technique exploiting unlabeled and labeled data to achieve better classification performance than using labeled data alone and is particularly useful with limited labeled data. This thesis explores the impact of different parameters on …
Generative Adversarial Networks for Improving Face Classification
2017
Master's thesis Information- and communication technology IKT590 - University of Agder 2017 Facial recognition can be applied in a wide variety of cases, including entertainment purposes and biometric security. In this thesis we take a look at improving the results of an existing facial recognition approach by utilizing generative adversarial networks to improve the existing dataset. The training data was taken from the LFW dataset[4] and was preprocessed using OpenCV[2] for face detection. The faces in the dataset was cropped and resized so every image is the same size and can easily be passed to a convolutional neural network. To the best of our knowledge no generative adversarial network…
Semi-supervised classification using tree-based self-organizing maps
2011
Published version of an article from the following onference prodeedings: AI 2011: Advances in Artificial Intelligence. Also available from the publisher on SpringerLink: http://dx.doi.org/10.1007/978-3-642-25832-9_3 This paper presents a classifier which uses a tree-based Neural Network (NN), and uses both, unlabeled and labeled instances. First, we learn the structure of the data distribution in an unsupervised manner. After convergence, and once labeled data become available, our strategy tags each of the clusters according to the evidence provided by the instances. Unlike other neighborhood-based schemes, our classifier uses only a small set of representatives whose cardinality can be m…
Engineering students approaching the mathematics textbook as a potential learning tool – opportunities and constraints
2016
Doktorgradsavhandling It is usually assumed that the students at tertiary level work intensively and individually with the new mathematical concepts (Wood, 2001). In this context the mathematics textbook might be an important learning tool. This thesis addresses the issue of what factors might influence the role of the mathematics textbook as a learning tool. The study is situated in the context of the basic mathematics course taken by first-year engineering students. A brief pilot study indicated that a majority of the students preferred using lecture notes rather than the textbook although in the beginning of the semester they perceived the textbook as being important when learning mathem…
Modeling a teacher in a tutorial-like system using Learning Automata
2012
Published version of a chapter in the book: Transactions on Computational Collective Intelligence VIII. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-34645-3_2 The goal of this paper is to present a novel approach to model the behavior of a Teacher in a Tutorial- like system. In this model, the Teacher is capable of presenting teaching material from a Socratic-type Domain model via multiple-choice questions. Since this knowledge is stored in the Domain model in chapters with different levels of complexity, the Teacher is able to present learning material of varying degrees of difficulty to the Students. In our model, we propose that the Teacher will be able to as…
The Finding and Dynamic Detection of Opinion Leaders in Social Network
2014
Published version of an article in the journal: Mathematical Problems in Engineering. Also available from the publisher at: http://dx.doi.org/10.1155/2014/328407 It is valuable for the real world to find the opinion leaders. Because different data sources usually have different characteristics, there does not exist a standard algorithm to find and detect the opinion leaders in different data sources. Every data source has its own structural characteristics, and also has its own detection algorithm to find the opinion leaders. Experimental results show the opinion leaders and theirs characteristics can be found among the comments from the Weibo social network of China, which is like Facebook…
Cloud screening and multitemporal unmixing of MERIS FR data
2007
The operational use of MERIS images can be hampered by the presence of clouds. This work presents a cloud screening algorithm that takes advantage of the high spectral and radiometric resolutions of MERIS and the specific location of some of its bands to increase the cloud detection accuracy. Moreover, the proposed algorithm provides a per-pixel probabilistic map of cloud abundance rather than a binary cloud presence flag. In order to test the proposed algorithm we propose a cloud screening validation method based on temporal series. In addition, we evaluate the impact of the cloud screening in a multitemporal unmixing application, where a temporal series of MERIS FR images acquired over Th…
More than experience? On the unique opportunities of virtual reality to afford a holistic experiential learning cycle
2021
Virtual reality has been proposed as a promising technology for higher education since the combination of immersive and interactive features enables experiential learning. However, previous studies did not distinguish between the different learning modes of the four-stage experiential learning cycle (i.e., concrete experience, reflective observation, abstract conceptualization, and active experimentation). With our study, we contribute a deeper understanding of how the unique opportunities of virtual reality can afford each of the four experiential learning modes. We conducted three design thinking workshops with interdisciplinary teams of students and lecturers. These workshops resulted in…
Evidence of delocalized excitons in amorphous solids
2010
We studied the temperature dependence of the absorption coefficient of amorphous ${\mathrm{SiO}}_{2}$ in the range from 8 to 17.5 eV obtained by Kramers-Kronig dispersion analysis of reflectivity spectra. We demonstrate the main excitonic resonance at 10.4 eV to feature a close Lorentzian shape redshifting with increasing temperature. This provides a strong evidence of excitons being delocalized notwithstanding the structural disorder intrinsic to amorphous ${\mathrm{SiO}}_{2}$. Excitons turn out to be coupled to an average phonon mode of 83 meV energy.